INDEX

Explanations

academic/scientific writing

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

LLU

-0.26

.Tools

-0.25

 complexion

-0.25

å±Ģéķ¿

-0.25

sig

-0.24

 propel

-0.24

éĽ¶åĶ®

-0.24

lbs

-0.24

ç¬ĳäºĨ

-0.24

POSITIVE LOGITS

ÙĪÙĬØ©

0.28

å±±è·¯

0.26

ningar

0.26

 anlaÅŁ

0.26

ë²

0.26

æº¯æºĲ

0.26

Cloud

0.25

ifle

0.25

 spot

0.25

ÑĨÐ¸Ð¾Ð½

0.25

Activations Density 0.002%

academic/scientific writing

No Comments

No Known Activations