INDEX

Explanations

ife

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

omid

-0.29

nev

-0.28

 triggering

-0.27

kov

-0.26

perienced

-0.26

AUTO

-0.25

rete

-0.25

Ø²Ø§ÙĦ

-0.24

AAD

-0.24

Gatt

-0.24

POSITIVE LOGITS

agher

0.29

¦Ĥ

0.28

 central

0.27

 Cond

0.26

atted

0.25

 cond

0.25

itable

0.25

ritable

0.25

ebra

0.25

Cond

0.24

Activations Density 0.791%

ife

No Comments

No Known Activations