INDEX

Explanations

Vague, multiple topics

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_32.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.32.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

hy

-0.26

Mixed

-0.26

Hai

-0.26

åĲī

-0.25

-abs

-0.25

è´ª

-0.25

çĮĹ

-0.25

ahi

-0.25

Fin

-0.24

 Heavy

-0.24

POSITIVE LOGITS

 Nichols

0.27

è³ĵ

0.25

å®¾

0.25

æĩ

0.25

icional

0.25

ubbo

0.25

å¨ĺ

0.25

 Armour

0.25

 DataRow

0.25

matrix

0.24

Activations Density 0.001%

Vague, multiple topics

No Comments

No Known Activations