INDEX

Explanations

scientific texts

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_33.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.33.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

iard

-0.28

-org

-0.27

ollo

-0.26

lum

-0.25

 tiá»ĩn

-0.25

.anchor

-0.25

èµ°è·¯

-0.24

åħ¨å¤©

-0.24

itate

-0.24

ViewById

-0.23

POSITIVE LOGITS

éĥĳéĩį

0.28

egan

0.27

æľīåĪ©

0.26

åĭĴ

0.25

stra

0.25

 VÃ¢n

0.25

KT

0.25

èİĬ

0.24

nicos

0.24

uced

0.24

Activations Density 0.006%

scientific texts

No Comments

No Known Activations