INDEX

Explanations

Seeking help/advice

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_10.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.10.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

æ±°

-0.27

[#

-0.25

mps

-0.24

’Ãł

-0.24

usc

-0.24

atern

-0.24

itable

-0.23

uff

-0.23

agraph

-0.23

-UA

-0.23

POSITIVE LOGITS

rif

0.28

BW

0.28

than

0.27

Bey

0.26

å®¤

0.26

æľį

0.25

zig

0.24

 Cancel

0.24

zig

0.24

yles

0.23

Activations Density 0.002%

Seeking help/advice

No Comments

No Known Activations