INDEX

Explanations

you

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_1.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.1.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

enso

-0.26

ServerError

-0.25

 Bureau

-0.24

ukkit

-0.24

 Rookie

-0.24

eci

-0.23

åĩ¡

-0.23

edList

-0.23

åĪ©

-0.23

 peter

-0.23

POSITIVE LOGITS

äº¤

0.30

oint

0.28

hof

0.27

çĳĻ

0.27

å¹¹

0.26

å¥Ĺ

0.26

-fit

0.25

ħ§

0.25

owell

0.25

ystone

0.25

Activations Density 30.320%

you

No Comments

No Known Activations