INDEX

Explanations

only

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

(details

-0.27

wolf

-0.26

IPS

-0.26

.removeAttribute

-0.25

ziel

-0.25

åĲĪä½ľåħ³ç³»

-0.25

ÙĥØ©

-0.25

 spit

-0.24

éĢĲæŃ¥

-0.24

æ¤Ĵ

-0.24

POSITIVE LOGITS

 Blades

0.25

ixo

0.25

æ¯Ķäºļ

0.25

åĢ¨

0.24

 attending

0.24

STDOUT

0.24

ç¾Į

0.24

Ŀå§ĭ

0.24

abcdefghijkl

0.24

 assembled

0.24

Activations Density 0.003%

only

No Comments

No Known Activations