INDEX

Explanations

legal and clinical content

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

è¿Ľç¨ĭä¸Ń

-0.27

cl

-0.27

 condensed

-0.27

å·¥ç¨ĭå¸Ī

-0.26

bury

-0.26

power

-0.26

cly

-0.25

cle

-0.25

 power

-0.24

oline

-0.24

POSITIVE LOGITS

mps

0.31

åı¯ä»¥ä½¿

0.28

WithIdentifier

0.28

 nearer

0.26

å®ļå±ħ

0.26

åĲĳè®°èĢħ

0.25

æĸ¹å¼ıè¿Ľè¡Į

0.25

è¢«æįķ

0.25

 unst

0.25

idente

0.25

Activations Density 0.000%

legal and clinical content

No Comments

No Known Activations