INDEX

Explanations

code

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

å°ıæĹ¶åīį

-0.32

seau

-0.30

 live

-0.26

åĪĴ

-0.26

 contro

-0.25

çįŃ

-0.24

Lau

-0.24

xa

-0.24

WARE

-0.24

ï¼ļ</

-0.24

POSITIVE LOGITS

PLIC

0.28

beck

0.28

lic

0.27

ä¸įæİĴéĻ¤

0.26

pei

0.26

èĪħ

0.25

ç³ľ

0.25

extern

0.25

ople

0.24

éĹª

0.24

Activations Density 0.003%

code

No Comments

No Known Activations