INDEX

Explanations

wooden

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_25.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.25.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

gene

-0.28

toa

-0.26

ropri

-0.26

cient

-0.26

enas

-0.25

ä¼ĹæīĢ

-0.24

lessness

-0.24

lene

-0.24

eer

-0.24

cbc

-0.24

POSITIVE LOGITS

etheless

0.28

ifest

0.26

æľīæĦı

0.26

theless

0.25

éĵĽ

0.24

ÑĨÐµ

0.24

æĤ¯

0.24

ities

0.24

chaft

0.23

heid

0.23

Activations Density 0.227%

wooden

No Comments

No Known Activations