INDEX

Explanations

embeddings and annotations

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_0.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.0.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

udit

-0.29

umph

-0.25

 Jump

-0.25

Ð¿ÑĥÑģ

-0.25

fad

-0.25

idelity

-0.24

æģ¶åĮĸ

-0.24

bart

-0.24

gest

-0.24

paralle

-0.24

POSITIVE LOGITS

achten

0.29

åįķåħĥ

0.28

æľŁåĨħ

0.27

edly

0.26

æĨ¾

0.25

åŃ¦èĢħ

0.24

è¾¼

0.24

æĢľ

0.23

æī¹

0.23

Ð¸ÑĢÐ°

0.23

Activations Density 5.538%

embeddings and annotations

No Comments

No Known Activations