Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 415
    Prev
    Next
    INDEX
    Explanations

    references/reading

    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
    Leod
    -0.07
    ❄
    -0.07
    عامل
    -0.06
    漷
    -0.06
    從
    -0.06
     savings
    -0.06
    inston
    -0.06
     Instead
    -0.06
    ,url
    -0.06
     neces
    -0.06
    POSITIVE LOGITS
     Authority
    0.08
    ٳ
    0.08
    曛
    0.07
    _SYM
    0.07
     setStatus
    0.07
    产区
    0.07
     abrasive
    0.07
    <option
    0.07
    旗
    0.07
     fringe
    0.07
    Activations Density 0.035%

    No Known Activations