INDEX

Explanations

limb

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

pekt

-0.25

åĲİå¤ĩ

-0.25

éĴµ

-0.25

ä¸įä¸ĭ

-0.25

aste

-0.25

Ø±ÙĬÙģ

-0.24

æĬĬä½ł

-0.24

atisfaction

-0.24

[var

-0.24

reservation

-0.24

POSITIVE LOGITS

oref

0.29

fce

0.28

lab

0.27

LI

0.27

 Passing

0.26

orc

0.25

orbit

0.25

nation

0.25

ded

0.25

LI

0.25

Activations Density 0.000%

limb

No Comments

No Known Activations