INDEX

Explanations

Now

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

au

-0.28

æĬµ

-0.28

iture

-0.28

æĭħ

-0.27

 Minute

-0.25

 Econ

-0.25

ONY

-0.25

åħįç¨İ

-0.25

panel

-0.25

áº£o

-0.24

POSITIVE LOGITS

ourg

0.26

èĶĵ

0.26

mn

0.24

mn

0.24

æĹ¢æľī

0.24

 formulation

0.24

 spirit

0.23

 forms

0.23

ariant

0.23

éĩįéĩį

0.23

Activations Density 0.009%

Now

No Comments

No Known Activations