© 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. 19-RESID-POST-AA
    11. 8833
    Prev
    Next
    INDEX
    Explanations

    prove

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    فهم
    -0.08
     ):
    -0.07
     zou
    -0.07
    )—
    -0.06
    陎
    -0.06
     Eden
    -0.06
    rPid
    -0.06
     benefit
    -0.06
     builders
    -0.06
     besides
    -0.06
    POSITIVE LOGITS
    مواق
    0.07
     Tactics
    0.07
    -large
    0.07
     Leading
    0.07
     multis
    0.06
    _attributes
    0.06
    cis
    0.06
     cruc
    0.06
    -changing
    0.06
    .prot
    0.06
    Activations Density 0.046%

    No Known Activations