INDEX

Explanations

Grades and ratings

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.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

 unity

-0.26

 UNITY

-0.25

Unity

-0.25

æ¢¯éĺŁ

-0.25

unity

-0.25

çīĮçħ§

-0.24

_trees

-0.24

å¦Ĥæŀľæľī

-0.24

 spherical

-0.24

ä¸īä»£

-0.24

POSITIVE LOGITS

è¯Ħ

0.34

zial

0.29

 score

0.29

è¯Ħå®ļ

0.28

 Rating

0.28

å¹ħåº¦

0.28

 figure

0.27

score

0.27

è¯ĦåĪĨ

0.27

-score

0.26

Activations Density 0.009%

Grades and ratings

No Comments

No Known Activations