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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 626
    Prev
    Next
    INDEX
    Explanations

    its

    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
    idenav
    -0.08
    mscorlib
    -0.07
     reaching
    -0.07
    中关村
    -0.07
    entine
    -0.07
     достиг
    -0.07
    key
    -0.07
    מומחי
    -0.07
    inish
    -0.06
    (fin
    -0.06
    POSITIVE LOGITS
    _uploaded
    0.07
     Numer
    0.07
    _hover
    0.07
    ｳ
    0.07
    oze
    0.07
    isFunction
    0.07
    _INST
    0.06
    _FORMAT
    0.06
    .StringUtils
    0.06
    -piece
    0.06
    Activations Density 0.015%

    No Known Activations