INDEX

Explanations

simplify

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

Kro

-0.27

mers

-0.27

_continuous

-0.26

:index

-0.26

mare

-0.26

èĩ³æĸ¼

-0.24

,[],

-0.24

æ¹¾

-0.24

 constit

-0.24

 schedules

-0.23

POSITIVE LOGITS

ething

0.27

outed

0.27

ppy

0.26

ÑĨÐµÐ²

0.26

ich

0.25

urn

0.25

åĿļæĮģ

0.25

ulous

0.25

ite

0.24

orte

0.24

Activations Density 0.007%

simplify

No Comments

No Known Activations