INDEX

Explanations

translate

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

 táº¯c

-0.26

AAAA

-0.25

akedown

-0.25

æİ¥

-0.25

prung

-0.24

Lite

-0.24

elage

-0.24

lsi

-0.24

sitemap

-0.23

 reception

-0.23

POSITIVE LOGITS

éĺ´éĺ³

0.28

é¬¥

0.26

.flow

0.26

-bars

0.25

 sampled

0.25

å¦Ĵ

0.25

 heels

0.25

 Bars

0.25

å·´

0.25

imitives

0.25

Activations Density 0.001%

translate

No Comments

No Known Activations