INDEX

Explanations

0

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.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

counter

-0.28

ude

-0.27

getParam

-0.27

 counter

-0.26

otre

-0.25

 Voyage

-0.25

(strategy

-0.25

(fr

-0.24

 Years

-0.24

atitude

-0.24

POSITIVE LOGITS

WATCH

0.26

å®ŀåľ¨æĺ¯å¤ª

0.26

åĪ«

0.26

 revel

0.25

æĸĩåĮĸ

0.24

Sdk

0.24

hari

0.24

ETCH

0.24

INGTON

0.23

.dsl

0.23

Activations Density 0.351%

0

No Comments

No Known Activations