© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 942
    Prev
    Next
    INDEX
    Explanations

    helping someone up

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     innovation
    -0.07
    очный
    -0.07
     chaos
    -0.07
     ram
    -0.07
    ogenous
    -0.06
     Fore
    -0.06
    roller
    -0.06
    .Position
    -0.06
     goto
    -0.06
     Scott
    -0.06
    POSITIVE LOGITS
    _matrices
    0.07
     defaults
    0.07
     totalPrice
    0.06
    补齐
    0.06
     relu
    0.06
     Wäh
    0.06
    _STOP
    0.06
    �
    0.06
    �
    0.06
    (varargin
    0.06
    Activations Density 0.044%

    No Known Activations