© 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. 15-RESID-POST-AA
    11. 115627
    Prev
    Next
    INDEX
    Explanations

    sunrise

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _USB
    -0.07
     маш
    -0.07
     overload
    -0.07
    LOG
    -0.07
    ='<?
    -0.06
    .misc
    -0.06
    -plane
    -0.06
    _parms
    -0.06
     стан
    -0.06
    .Flag
    -0.06
    POSITIVE LOGITS
    実際に
    0.07
    呱
    0.07
     twentieth
    0.07
    rl
    0.07
    violent
    0.07
    Elapsed
    0.07
    new
    0.07
    مشروع
    0.06
    ᆰ
    0.06
    vertise
    0.06
    Activations Density 0.005%

    No Known Activations