INDEX

Explanations

distance and range

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ãĤŃãĥ¥

-0.27

igrams

-0.27

å¾ģæ±Ĥ

-0.26

è¾¹

-0.26

(bar

-0.25

amm

-0.25

 biÃªn

-0.24

åĬ¨

-0.24

priv

-0.24

éĽĨä½ĵ

-0.24

POSITIVE LOGITS

spread

0.32

Reach

0.31

 widen

0.30

 spread

0.28

wide

0.28

åľ°çĲĨ

0.28

Ð¿ÐµÑĩ

0.28

Spread

0.28

 Spread

0.28

 scopes

0.27

Activations Density 2.440%

distance and range

No Comments

No Known Activations