INDEX

Explanations

punishment and consequences

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

omat

-0.28

 spont

-0.26

ORMAT

-0.26

åĨ²

-0.26

omit

-0.26

omen

-0.26

ç²¾å½©

-0.25

æĸ°åŀĭåĨłçĬ¶

-0.25

 nearly

-0.25

 neat

-0.25

POSITIVE LOGITS

hti

0.27

ramento

0.25

 punishment

0.25

åºľ

0.25

 punishments

0.25

 flesh

0.25

 punitive

0.25

ç¿¦

0.25

æĳĽ

0.24

èµı

0.24

Activations Density 0.092%

punishment and consequences

No Comments

No Known Activations